HKUDS/Vibe-Trading · error · ValueError

criterion {criterion.criterion_id} is not satisfied

Error message

criterion {criterion.criterion_id} is not satisfied

What it means

A completion audit row carried a result value outside _COMPLETION_RESULTS (the allowed satisfied/satisfied_with_caveat/not_applicable set), so the criterion counts as unsatisfied and completion is refused.

Source

Thrown at agent/src/goal/store.py:913

        if row is None:
            raise ValueError(f"unknown claim_id: {claim_id}")
        return self._claim_from_row(row)

    def _validate_completion_audit(
        self,
        goal: GoalRecord,
        audit: list[AuditRow],
    ) -> None:
        criteria = self.list_criteria(goal.goal_id)
        rows_by_criterion = {row.criterion_id: row for row in audit}
        for criterion in criteria:
            if not criterion.required:
                continue
            row = rows_by_criterion.get(criterion.criterion_id)
            if row is None:
                raise ValueError(f"missing audit row for criterion {criterion.criterion_id}")
            if row.result not in _COMPLETION_RESULTS:
                raise ValueError(f"criterion {criterion.criterion_id} is not satisfied")
            if row.result in {"satisfied", "satisfied_with_caveat"} and not row.evidence_ids:
                raise ValueError("complete goals require verified evidence")
            if row.result == "not_applicable_user_accepted" and not row.notes.strip():
                raise ValueError("not-applicable criteria require acceptance notes")
            has_verified_evidence = False
            for evidence_id in row.evidence_ids:
                evidence = self._get_evidence(evidence_id)
                if evidence is None or evidence.goal_id != goal.goal_id:
                    raise ValueError(f"unknown evidence_id: {evidence_id}")
                if evidence.criterion_id != criterion.criterion_id:
                    raise ValueError(
                        f"evidence {evidence_id} does not match criterion {criterion.criterion_id}"
                    )
                if evidence.verification_status == "verified":
                    has_verified_evidence = True
            if row.result in {"satisfied", "satisfied_with_caveat"} and not has_verified_evidence:
                raise ValueError("complete goals require verified evidence")

View on GitHub (pinned to 80ffdda44c)

Solutions

1. Use only the allowed result literals: satisfied, satisfied_with_caveat, not_applicable_user_accepted (check _COMPLETION_RESULTS in your version)
2. Validate/normalize LLM-produced result strings against the allowed set before building audit rows
3. If a criterion truly is unsatisfied, the goal cannot be completed yet — gather evidence first

Example fix

// before
AuditRow(criterion_id="c1", result="done", evidence_ids=[...])
// after
_ALLOWED = {"satisfied", "satisfied_with_caveat", "not_applicable_user_accepted"}
result = result if result in _ALLOWED else "satisfied"
AuditRow(criterion_id="c1", result=result, evidence_ids=[...])

ALLOWED = {"satisfied", "satisfied_with_caveat", "not_applicable_user_accepted"}
assert all(row.result in ALLOWED for row in audit), [r.result for r in audit if r.result not in ALLOWED]

def is_valid_result(result: str) -> bool:
    return result in {"satisfied", "satisfied_with_caveat", "not_applicable_user_accepted"}

except ValueError as e: if 'not satisfied' in str(e): normalize result strings and re-validate before retrying

When it happens

Trigger: update_status with an audit row whose result is e.g. "unsatisfied", "pending", or a typo like "satisifed".

Common situations: Result strings built by LLM output or dynamic code; enum/str mismatch after a version change renaming result values.

Related errors

• missing audit row for criterion {criterion.criterion_id}
• complete goals require verified evidence
• not-applicable criteria require acceptance notes
• unknown evidence_id: {evidence_id}
• evidence {evidence_id} does not match criterion {criterion.c

AI-assisted analysis of HKUDS/Vibe-Trading@80ffdda44c (2026-08-28). Data as JSON: /api/errors/01e49369ae006164. Report an issue: GitHub.